longevity-scholar

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries the public Semantic Scholar API (via scripts/query_longevity_papers.py as described in SKILL.md Steps 3–4) and requires the agent to read and synthesize titles, abstracts, and metadata from those third-party papers, which could materially influence its subsequent actions or decisions.